© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118425
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urat
    -0.08
    zcze
    -0.08
    sanitize
    -0.08
    olson
    -0.08
    esium
    -0.08
    رÛĮز
    -0.07
    udur
    -0.07
    peria
    -0.07
    rawer
    -0.07
    assin
    -0.07
    POSITIVE LOGITS
     each
    0.07
     opport
    0.06
    each
    0.06
    rough
    0.06
     dispatch
    0.05
    emy
    0.05
     collect
    0.05
    è¼
    0.05
     Leisure
    0.05
    ex
    0.05
    Activations Density 0.060%

    No Known Activations